DPDK patches and discussions
 help / color / mirror / Atom feed
* [dpdk-dev] [PATCH] arch/arm: optimization for memcpy on AArch64
@ 2017-11-27  7:49 Herbert Guan
  2017-11-29 12:31 ` Jerin Jacob
                   ` (4 more replies)
  0 siblings, 5 replies; 26+ messages in thread
From: Herbert Guan @ 2017-11-27  7:49 UTC (permalink / raw)
  To: jerin.jacob, jianbo.liu, dev; +Cc: Herbert Guan

This patch provides an option to do rte_memcpy() using 'restrict'
qualifier, which can induce GCC to do optimizations by using more
efficient instructions, providing some performance gain over memcpy()
on some AArch64 platforms/enviroments.

The memory copy performance differs between different AArch64
platforms. And a more recent glibc (e.g. 2.23 or later)
can provide a better memcpy() performance compared to old glibc
versions. It's always suggested to use a more recent glibc if
possible, from which the entire system can get benefit. If for some
reason an old glibc has to be used, this patch is provided for an
alternative.

This implementation can improve memory copy on some AArch64
platforms, when an old glibc (e.g. 2.19, 2.17...) is being used.
It is disabled by default and needs "RTE_ARCH_ARM64_MEMCPY"
defined to activate. It's not always proving better performance
than memcpy() so users need to run DPDK unit test
"memcpy_perf_autotest" and customize parameters in "customization
section" in rte_memcpy_64.h for best performance.

Compiler version will also impact the rte_memcpy() performance.
It's observed on some platforms and with the same code, GCC 7.2.0
compiled binary can provide better performance than GCC 4.8.5. It's
suggested to use GCC 5.4.0 or later.

Signed-off-by: Herbert Guan <herbert.guan@arm.com>
---
 .../common/include/arch/arm/rte_memcpy_64.h        | 193 +++++++++++++++++++++
 1 file changed, 193 insertions(+)

diff --git a/lib/librte_eal/common/include/arch/arm/rte_memcpy_64.h b/lib/librte_eal/common/include/arch/arm/rte_memcpy_64.h
index b80d8ba..1f42b3c 100644
--- a/lib/librte_eal/common/include/arch/arm/rte_memcpy_64.h
+++ b/lib/librte_eal/common/include/arch/arm/rte_memcpy_64.h
@@ -42,6 +42,197 @@
 
 #include "generic/rte_memcpy.h"
 
+#ifdef RTE_ARCH_ARM64_MEMCPY
+#include <rte_common.h>
+#include <rte_branch_prediction.h>
+
+/*******************************************************************************
+ * The memory copy performance differs on different AArch64 micro-architectures.
+ * And the most recent glibc (e.g. 2.23 or later) can provide a better memcpy()
+ * performance compared to old glibc versions. It's always suggested to use a
+ * more recent glibc if possible, from which the entire system can get benefit.
+ *
+ * This implementation improves memory copy on some aarch64 micro-architectures,
+ * when an old glibc (e.g. 2.19, 2.17...) is being used. It is disabled by
+ * default and needs "RTE_ARCH_ARM64_MEMCPY" defined to activate. It's not
+ * always providing better performance than memcpy() so users need to run unit
+ * test "memcpy_perf_autotest" and customize parameters in customization section
+ * below for best performance.
+ *
+ * Compiler version will also impact the rte_memcpy() performance. It's observed
+ * on some platforms and with the same code, GCC 7.2.0 compiled binaries can
+ * provide better performance than GCC 4.8.5 compiled binaries.
+ ******************************************************************************/
+
+/**************************************
+ * Beginning of customization section
+ **************************************/
+#define ALIGNMENT_MASK 0x0F
+#ifndef RTE_ARCH_ARM64_MEMCPY_STRICT_ALIGN
+// Only src unalignment will be treaed as unaligned copy
+#define IS_UNALIGNED_COPY(dst, src) ((uintptr_t)(dst) & ALIGNMENT_MASK)
+#else
+// Both dst and src unalignment will be treated as unaligned copy
+#define IS_UNALIGNED_COPY(dst, src) \
+		(((uintptr_t)(dst) | (uintptr_t)(src)) & ALIGNMENT_MASK)
+#endif
+
+
+// If copy size is larger than threshold, memcpy() will be used.
+// Run "memcpy_perf_autotest" to determine the proper threshold.
+#define ALIGNED_THRESHOLD       ((size_t)(0xffffffff))
+#define UNALIGNED_THRESHOLD     ((size_t)(0xffffffff))
+
+
+/**************************************
+ * End of customization section
+ **************************************/
+#ifdef RTE_TOOLCHAIN_GCC
+#if (GCC_VERSION < 50400)
+#warning "The GCC version is quite old, which may result in sub-optimal \
+performance of the compiled code. It is suggested that at least GCC 5.4.0 \
+be used."
+#endif
+#endif
+
+static inline void __attribute__ ((__always_inline__))
+rte_mov16(uint8_t *restrict dst, const uint8_t *restrict src)
+{
+	__int128 * restrict dst128 = (__int128 * restrict)dst;
+	const __int128 * restrict src128 = (const __int128 * restrict)src;
+	*dst128 = *src128;
+}
+
+static inline void __attribute__ ((__always_inline__))
+rte_mov32(uint8_t *restrict dst, const uint8_t *restrict src)
+{
+	__int128 * restrict dst128 = (__int128 * restrict)dst;
+	const __int128 * restrict src128 = (const __int128 * restrict)src;
+	dst128[0] = src128[0];
+	dst128[1] = src128[1];
+}
+
+static inline void __attribute__ ((__always_inline__))
+rte_mov48(uint8_t *restrict dst, const uint8_t *restrict src)
+{
+	__int128 * restrict dst128 = (__int128 * restrict)dst;
+	const __int128 * restrict src128 = (const __int128 * restrict)src;
+	dst128[0] = src128[0];
+	dst128[1] = src128[1];
+	dst128[2] = src128[2];
+}
+
+static inline void __attribute__ ((__always_inline__))
+rte_mov64(uint8_t *restrict dst, const uint8_t *restrict src)
+{
+	__int128 * restrict dst128 = (__int128 * restrict)dst;
+	const __int128 * restrict src128 = (const __int128 * restrict)src;
+	dst128[0] = src128[0];
+	dst128[1] = src128[1];
+	dst128[2] = src128[2];
+	dst128[3] = src128[3];
+}
+
+static inline void __attribute__ ((__always_inline__))
+rte_mov128(uint8_t *restrict dst, const uint8_t *restrict src)
+{
+	rte_mov64(dst, src);
+	rte_mov64(dst + 64, src + 64);
+}
+
+static inline void __attribute__ ((__always_inline__))
+rte_mov256(uint8_t *restrict dst, const uint8_t *restrict src)
+{
+	rte_mov128(dst, src);
+	rte_mov128(dst + 128, src + 128);
+}
+
+static inline void __attribute__ ((__always_inline__))
+rte_memcpy_lt16(uint8_t *restrict dst, const uint8_t *restrict src, size_t n)
+{
+	if (n & 0x08) {
+		/* copy 8 ~ 15 bytes */
+		*(uint64_t *)dst = *(const uint64_t *)src;
+		*(uint64_t *)(dst - 8 + n) = *(const uint64_t *)(src - 8 + n);
+	} else if (n & 0x04) {
+		/* copy 4 ~ 7 bytes */
+		*(uint32_t *)dst = *(const uint32_t *)src;
+		*(uint32_t *)(dst - 4 + n) = *(const uint32_t *)(src - 4 + n);
+	} else if (n & 0x02) {
+		/* copy 2 ~ 3 bytes */
+		*(uint16_t *)dst = *(const uint16_t *)src;
+		*(uint16_t *)(dst - 2 + n) = *(const uint16_t *)(src - 2 + n);
+	} else if (n & 0x01) {
+		/* copy 1 byte */
+		*dst = *src;
+	}
+}
+
+static inline void __attribute__ ((__always_inline__))
+rte_memcpy_ge16_lt64
+(uint8_t *restrict dst, const uint8_t *restrict src, size_t n)
+{
+	if (n == 16) {
+		rte_mov16(dst, src);
+	} else if (n <= 32) {
+		rte_mov16(dst, src);
+		rte_mov16(dst - 16 + n, src - 16 + n);
+	} else if (n <= 48) {
+		rte_mov32(dst, src);
+		rte_mov16(dst - 16 + n, src - 16 + n);
+	} else {
+		rte_mov48(dst, src);
+		rte_mov16(dst - 16 + n, src - 16 + n);
+	}
+}
+
+static inline void __attribute__ ((__always_inline__))
+rte_memcpy_ge64(uint8_t *restrict dst, const uint8_t *restrict src, size_t n)
+{
+	do {
+		rte_mov64(dst, src);
+		src += 64;
+		dst += 64;
+		n -= 64;
+	} while (likely(n >= 64));
+
+	if (likely(n)) {
+		if (n > 48)
+			rte_mov64(dst - 64 + n, src - 64 + n);
+		else if (n > 32)
+			rte_mov48(dst - 48 + n, src - 48 + n);
+		else if (n > 16)
+			rte_mov32(dst - 32 + n, src - 32 + n);
+		else
+			rte_mov16(dst - 16 + n, src - 16 + n);
+	}
+}
+
+static inline void *__attribute__ ((__always_inline__))
+rte_memcpy(void *restrict dst, const void *restrict src, size_t n)
+{
+	if (n < 16) {
+		rte_memcpy_lt16((uint8_t *)dst, (const uint8_t *)src, n);
+		return dst;
+	}
+	if (n < 64) {
+		rte_memcpy_ge16_lt64((uint8_t *)dst, (const uint8_t *)src, n);
+		return dst;
+	}
+	__builtin_prefetch(src, 0, 0);
+	__builtin_prefetch(dst, 1, 0);
+	if (likely(
+		  (!IS_UNALIGNED_COPY(dst, src) && n <= ALIGNED_THRESHOLD)
+		   || (IS_UNALIGNED_COPY(dst, src) && n <= UNALIGNED_THRESHOLD)
+		  )) {
+		rte_memcpy_ge64((uint8_t *)dst, (const uint8_t *)src, n);
+		return dst;
+	} else
+		return memcpy(dst, src, n);
+}
+
+
+#else
 static inline void
 rte_mov16(uint8_t *dst, const uint8_t *src)
 {
@@ -80,6 +271,8 @@
 
 #define rte_memcpy(d, s, n)	memcpy((d), (s), (n))
 
+#endif
+
 #ifdef __cplusplus
 }
 #endif
-- 
1.8.3.1

^ permalink raw reply	[flat|nested] 26+ messages in thread

end of thread, other threads:[~2018-01-20 16:21 UTC | newest]

Thread overview: 26+ messages (download: mbox.gz / follow: Atom feed)
-- links below jump to the message on this page --
2017-11-27  7:49 [dpdk-dev] [PATCH] arch/arm: optimization for memcpy on AArch64 Herbert Guan
2017-11-29 12:31 ` Jerin Jacob
2017-12-03 12:37   ` Herbert Guan
2017-12-15  4:06     ` Jerin Jacob
2017-12-18  2:51       ` Herbert Guan
2017-12-18  4:17         ` Jerin Jacob
2017-12-02  7:33 ` Pavan Nikhilesh Bhagavatula
2017-12-03 12:38   ` Herbert Guan
2017-12-03 14:20     ` Pavan Nikhilesh Bhagavatula
2017-12-04  7:14       ` Herbert Guan
2017-12-05  6:02 ` [dpdk-dev] [PATCH v2] " Herbert Guan
2017-12-18  2:54 ` [dpdk-dev] [PATCH v3] " Herbert Guan
2017-12-18  7:43   ` Jerin Jacob
2017-12-19  5:33     ` Herbert Guan
2017-12-19  7:24       ` Jerin Jacob
2017-12-21  5:33   ` [dpdk-dev] [PATCH v4] " Herbert Guan
2018-01-03 13:35     ` Jerin Jacob
2018-01-04 10:23       ` Herbert Guan
2018-01-04 10:20 ` [dpdk-dev] [PATCH v5] " Herbert Guan
2018-01-12 17:03   ` Thomas Monjalon
2018-01-15 10:57     ` Herbert Guan
2018-01-15 11:37       ` Thomas Monjalon
2018-01-18 23:54         ` Thomas Monjalon
2018-01-19  6:16           ` [dpdk-dev] 答复: " Herbert Guan
2018-01-19  6:10   ` [dpdk-dev] [PATCH v6] arch/arm: optimization for memcpy on ARM64 Herbert Guan
2018-01-20 16:21     ` Thomas Monjalon

This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).